INDEX

Explanations

prepositions followed by nouns

The neuron fires on common relational words—especially prepositions (e.g. “to,” “in,” “around,” “for,” “on,” “with”) that signal spatial, directional, or structural relationships.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

to

-1.47

and

-1.45

but

-1.39

 with

-1.37

 этих

-1.36

-1.28

 often

-1.28

is

-1.25

An

-1.25

-1.24

POSITIVE LOGITS

 helicóptero

1.45

meye

1.38

Odpowiedz

1.35

ástica

1.33

 inſ

1.32

 rembourse

1.30

توضیحات

1.30

 uska

1.29

bánh

1.28

icts

1.27

Activations Density 0.047%